{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:46:53Z","timestamp":1744181213539,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319969824"},{"type":"electronic","value":"9783319969831"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-96983-1_17","type":"book-chapter","created":{"date-parts":[[2018,7,31]],"date-time":"2018-07-31T15:50:06Z","timestamp":1533052206000},"page":"235-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving GPU Cache Hierarchy Performance with a Fetch and Replacement Cache"],"prefix":"10.1007","author":[{"given":"Francisco","family":"Candel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salvador","family":"Petit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro","family":"Valero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julio","family":"Sahuquillo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,1]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Huang, S., Xiao, S., Feng, W.: On the energy efficiency of graphics processing units for scientific computing. In: Proceedings of the IEEE International Symposium on Parallel and Distributed Processing, pp. 1\u20138 (2009)","DOI":"10.1109\/IPDPS.2009.5160980"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Glenis, A., Petridis, S.: Performance and energy characterization of high-performance low-cost cornerness detection on GPUs and multicores. In: Proceedings of the 5th International Conference on Information, Intelligence, Systems and Applications, pp. 181\u2013186 (2014)","DOI":"10.1109\/IISA.2014.6878727"},{"key":"17_CR3","unstructured":"Top500.org: Top500 Supercomputer Sites. http:\/\/top500.org"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Ubal, R., Jang, B., Mistry, P., Schaa, D., Kaeli, D.: Multi2Sim: a simulation framework for CPU-GPU computing. In: Proceedings of the 21st International Conference on Parallel Architectures and Compilation Techniques, pp. 335\u2013344 (2012)","DOI":"10.1145\/2370816.2370865"},{"key":"17_CR5","unstructured":"AMD: Southern Islands Series Instruction Set Architecture (2012)"},{"key":"17_CR6","unstructured":"AMD: AMD Graphics Cores Next (GCN) Architecture White Paper (2012)"},{"key":"17_CR7","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1016\/j.future.2017.02.012","volume":"82","author":"F Candel","year":"2018","unstructured":"Candel, F., Petit, S., Sahuquillo, J., Duato, J.: Accurately modeling the on-chip and off-chip GPU memory subsystem. Future Gener. Comput. Syst. 82, 510\u2013519 (2018)","journal-title":"Future Gener. Comput. Syst."},{"key":"17_CR8","unstructured":"AMD: AMD Accelerated Parallel Processing (APP) Software Development Kit (SDK) (2012)"},{"issue":"8","key":"17_CR9","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1109\/TVLSI.2013.2278025","volume":"22","author":"S Mu","year":"2014","unstructured":"Mu, S., Deng, Y., Chen, Y., Li, H., Pan, J., Zhang, W., Wang, Z.: Orchestrating cache management and memory scheduling for GPGPU applications. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 22(8), 1803\u20131814 (2014)","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Jia, W., Shaw, K.A., Martonosi, M.: MRPB: memory request prioritization for massively parallel processors. In: Proceedings of the IEEE 20th International Symposium on High Performance Computer Architecture, pp. 272\u2013283 (2014)","DOI":"10.1109\/HPCA.2014.6835938"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Sethia, A., Jamshidi, D.A., Mahlke, S.: Mascar: speeding up GPU warps by reducing memory pitstops. In: Proceedings of the IEEE 21st International Symposium on High Performance Computer Architecture, pp. 174\u2013185 (2015)","DOI":"10.1109\/HPCA.2015.7056031"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., Song, S.L., Dai, H., Sidelnik, A., Hari, S.K.S., Zhou, H.: Locality-driven dynamic GPU cache bypassing. In: Proceedings of the 29th International ACM Conference on Supercomputing, pp. 67\u201377 (2015)","DOI":"10.1145\/2751205.2751237"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Liang, Y., Xie, X., Wang, Y., Sun, G., Wang, T.: Optimizing cache bypassing and warp scheduling for GPUs. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. (2018, to appear)","DOI":"10.1109\/TCAD.2017.2764886"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Li, B., Sun, J., Annavaram, M., Kim, N.S.: Elastic-cache: GPU cache architecture for efficient fine- and coarse-grained cache-line management. In: Proceedings of the IEEE International Parallel and Distributed Processing Symposium, pp. 82\u201391 (2017)","DOI":"10.1109\/IPDPS.2017.81"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Gebhart, M., Keckler, S.W., Khailany, B., Krashinsky, R., Dally, W.J.: Unifying primary cache, scratch, and register file memories in a throughput processor. In: Proceedings of the IEEE\/ACM 45th Annual International Symposium on Microarchitecture, pp. 96\u2013106 (2012)","DOI":"10.1109\/MICRO.2012.18"},{"issue":"3","key":"17_CR16","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/TPDS.2017.2773516","volume":"29","author":"S Mu","year":"2018","unstructured":"Mu, S., Deng, Y., Chen, Y., Li, H., Pan, J., Zhang, W., Wang, Z.: IBOM: an integrated and balanced on-chip memory for high performance GPGPUs. IEEE Trans. Parallel Distrib. Syst. 29(3), 586\u2013599 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"24","key":"17_CR17","first-page":"1","volume":"29","author":"J Wang","year":"2017","unstructured":"Wang, J., Fan, F., Jiang, L., Liang, X., Jing, N.: Incorporating selective victim cache into GPGPU for high-performance computing. Wiley Concurr. Comput.: Pract. Exp. 29(24), 1\u201311 (2017)","journal-title":"Wiley Concurr. Comput.: Pract. Exp."},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Sankaranarayanan, A., Ardestani, E.K., Briz, J.L., Renau, J.: An energy efficient GPGPU memory hierarchy with tiny incoherent caches. In: Proceedings of the International Symposium on Low Power Electronics and Design, pp. 9\u201314 (2013)","DOI":"10.1109\/ISLPED.2013.6629259"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2018: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-96983-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T01:06:02Z","timestamp":1659315962000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-96983-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319969824","9783319969831"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-96983-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"1 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}